{"id":"https://openalex.org/W4412945636","doi":"https://doi.org/10.18653/v1/2025.acl-long.351","title":"M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation","display_name":"M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945636","doi":"https://doi.org/10.18653/v1/2025.acl-long.351"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.351","doi":"https://doi.org/10.18653/v1/2025.acl-long.351","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.351","pdf_url":null,"source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.20127","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078947610","display_name":"Zhaopeng Feng","orcid":"https://orcid.org/0000-0002-6396-3184","observed_orcids":["https://orcid.org/0000-0002-6396-3184"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaopeng Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069491635","display_name":"Jianwen Su","orcid":"https://orcid.org/0000-0002-4637-1339","observed_orcids":["https://orcid.org/0000-0002-4637-1339"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayuan Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiamei Zheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiamei Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiahan Ren","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahan Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456256","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0002-4941-8622","observed_orcids":["https://orcid.org/0000-0002-4941-8622"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110293836","display_name":"Jian Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058072839","display_name":"Hongwei Wang","orcid":"https://orcid.org/0000-0001-6118-6505","observed_orcids":["https://orcid.org/0000-0001-6118-6505","https://orcid.org/0000-0002-3657-2874","https://orcid.org/0000-0002-8403-1538"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongwei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024343415","display_name":"Zuozhu Liu","orcid":"https://orcid.org/0000-0002-7816-502X","observed_orcids":["https://orcid.org/0000-0002-7816-502X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuozhu Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.8637,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.97952934,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7084","last_page":"7107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9502000212669373,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9502000212669373,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10759","display_name":"Translation Studies and Practices","score":0.013000000268220901,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0052999998442828655,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/machine-translation-evaluation","display_name":"machine translation evaluation","score":0.9629999995231628},{"id":"https://openalex.org/keywords/multi-agent-debate","display_name":"multi-agent debate","score":0.8859999775886536},{"id":"https://openalex.org/keywords/multidimensional-assessment","display_name":"multidimensional assessment","score":0.7300000190734863},{"id":"https://openalex.org/keywords/human-evaluation","display_name":"human evaluation","score":0.3370000123977661},{"id":"https://openalex.org/keywords/translation-quality-assessment","display_name":"translation quality assessment","score":0.3889999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6917871832847595},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5145573019981384},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4367351233959198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41665852069854736},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05704665184020996},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.351","doi":"https://doi.org/10.18653/v1/2025.acl-long.351","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.351","pdf_url":null,"source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.20127","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.20127","pdf_url":"https://arxiv.org/pdf/2412.20127","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.20127","doi":"https://doi.org/10.48550/arxiv.2412.20127","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.20127","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.20127","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.20127","pdf_url":"https://arxiv.org/pdf/2412.20127","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945636.pdf","grobid_xml":"https://content.openalex.org/works/W4412945636.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W3011059803","https://openalex.org/W4396701345","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"Recent":[0],"advancements":[1,65],"in":[2,22],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"have":[7],"given":[8],"rise":[9],"to":[10,17,83,100],"the":[11,23,85,141],"LLM-as-a-judge":[12,31,55,116,152],"paradigm,":[13],"showcasing":[14],"their":[15],"potential":[16],"deliver":[18],"human-like":[19],"judgments.":[20],"However,":[21],"field":[24],"of":[25,35,89,143],"machine":[26],"translation":[27],"(MT)":[28],"evaluation,":[29],"current":[30],"methods":[32,117],"fall":[33],"short":[34],"learned":[36],"automatic":[37,124],"metrics.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"propose":[43],"Multidimensional":[44],"Multi-Agent":[45],"Debate":[46],"(M-MAD),":[47],"a":[48,96,130,148],"systematic":[49],"LLM-based":[50],"multi-agent":[51,81],"framework":[52,145],"for":[53,76,151],"advanced":[54],"MT":[56],"evaluation.":[57],"Our":[58,154],"findings":[59],"demonstrate":[60],"that":[61,109],"M-MAD":[62,110],"achieves":[63],"significant":[64],"by":[66,129],"(1)":[67],"decoupling":[68],"heuristic":[69],"MQM":[70],"criteria":[71],"into":[72,95],"distinct":[73],"evaluation":[74,98],"dimensions":[75],"fine-grained":[77],"assessments;":[78],"(2)":[79],"employing":[80],"debates":[82],"harness":[84],"collaborative":[86],"reasoning":[87],"capabilities":[88],"LLMs;":[90],"(3)":[91],"synthesizing":[92],"dimension-specific":[93],"results":[94],"final":[97],"judgment":[99],"ensure":[101],"robust":[102],"and":[103,138,156],"reliable":[104],"outcomes.":[105],"Comprehensive":[106],"experiments":[107],"show":[108],"not":[111],"only":[112],"outperforms":[113],"all":[114],"existing":[115],"but":[118],"also":[119],"competes":[120],"with":[121],"state-of-the-art":[122],"reference-based":[123],"metrics,":[125],"even":[126],"when":[127],"powered":[128],"suboptimal":[131],"model":[132],"like":[133],"GPT-4o":[134],"mini.":[135],"Detailed":[136],"ablations":[137],"analysis":[139],"highlight":[140],"superiority":[142],"our":[144],"design,":[146],"offering":[147],"fresh":[149],"perspective":[150],"paradigm.":[153],"code":[155],"data":[157],"are":[158],"publicly":[159],"available":[160],"at":[161],"https://github.com/SU-JIAYUAN/M-MAD.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":8}],"updated_date":"2026-10-17T09:40:24.721904","created_date":"2025-10-10T00:00:00"}